Irtiza Hasan
Senior Computer Vision Researcher at Immersal
Helsinki, Mainland Finland
Summary
👤
Senior🎓
Top SchoolIrtiza Hasan is a Senior Computer Vision Researcher with nine years of experience applying deep learning to visual perception problems across AR/VR, autonomous systems, and industrial applications. Based in Helsinki, he currently focuses on visual localization, detection/segmentation, classification and forecasting at Immersal after roles at Huawei and ADNOC-AIQ where he translated research into production solutions. His PhD-level research background and prior work at Inception Institute of AI make him a strong practitioner of robust, generalizable models—he was a principal developer of the Pedestron pedestrian detection framework used in CVPR-related research. Comfortable moving models from lab to field, he has practical experience tuning Faster R-CNN, RetinaNet, Cascade R-CNN and HTC pipelines for city-scale datasets. Colleagues describe him as research-driven but product-minded, bridging open-source contributions and deployed perception systems.
9 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at Università degli Studi di VeronaMaster's Degree, Computer Vision and Signal Processing, Master's Degree, Computer Vision and Signal Processing at University of OuluBachelor of Science (B.Sc.), Computer Science, Bachelor of Science (B.Sc.), Computer Science at Air University
English, Urdu, Finnish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (10)
retinanet10
computer-vision10
faster-rcnn10
resnet9
vnet9
net9
object-detection9
machine-learning8
python8
configuration-management7
Programming languages (3)
Github contributions (5)
hasanirtiza/Pedestron
Mar 2020 - Oct 2022
[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021
Role in this project:
ML Engineer
ML EngineerContributions:155 commits, 8 PRs, 141 pushes in 2 years 7 months
Contributions summary:Irtiza primarily contributed to the project by adding and modifying configuration files for various object detection models, specifically focusing on Faster R-CNN, RetinaNet, Cascade R-CNN, and HTC architectures. Their contributions included defining model settings, training configurations, and dataset parameters for pedestrian detection on the CityPersons and EuroCity datasets. The user also added and updated scripts for dataset conversion and evaluation, indicating a focus on model training and evaluation within the pedestrian detection domain.
benchmarkingretinanetelephantpedestrian-detectionpedestrian
hasanirtiza/PedesFormer-Transformer-Networks-For-Pedestrian-Detection
Nov 2021 - May 2022
Contributions:22 commits, 21 pushes, 1 branch in 6 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.